© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8136
    Prev
    Next
    INDEX
    Explanations

    references to messages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '}>
    -0.88
     ingenu
    -0.78
    nere
    -0.78
    ']?>
    -0.76
     }}$}
    -0.76
     Mele
    -0.74
    parentElement
    -0.74
    PropertyGroup
    -0.74
    

    -0.73
    ope
    -0.72
    POSITIVE LOGITS
    msg
    1.45
     msg
    1.45
     Msg
    1.28
    getMsg
    1.15
     msgs
    1.14
    setMsg
    1.06
    Msgs
    1.04
    Msg
    0.99
     errorMsg
    0.99
     folic
    0.86
    Activations Density 0.044%

    No Known Activations